vllm
serve
/opt/local-models/qwen36-27b-hf
--served-model-name
Qwen3.6-27B
--enable-auto-tool-choice
--tool-call-parser
qwen3_coder
--dtype
half
--host
0.0.0.0
--port
8001
--tensor-parallel-size
8
--max-model-len
131072
--gpu-memory-utilization
0.95
--trust-remote-code
--generation-config
vllm
-O=3
--reasoning-parser
qwen3
--async-scheduling
--hf-overrides
{"architectures":["Qwen3_5ForCausalLM"]}
--language-model-only
--max-num-seqs
2
--max-num-batched-tokens
4
--no-enable-prefix-caching
